New AI Tool Helps Manage COVID-19

New Artificial Intelligence technology developed by researchers at Waterloo Engineering can assess the severity of COID-19 cases with a high rate of accuracy.

This research is part of a COVID-Net open-source initiative launched over a year ago. It consists of researchers from Waterloo and spin-off startup company DarwinAI, as well as radiologists from the Stony Brook School of Medicine and the Montefiore Medical Center in New York.

The AI was trained to examine the extent of infection in the lungs of COVID-19 patients based on their chest x-rays. The results were then compared to those of expert radiologists.

For both opacity and extent, which are strong indicators of the severity of diseases, the AI software’s prediction aligned with the scores of the human experts.

Alexander Wong, Systems Design Engineering Professor and co-founder of DarwinAI said the technology could help doctors manage cases.

‘Assessing the severity of a patient with COVID-19 is a critical step in the clinical workflow for determining the best course of action for treatment and care, be it admitting the patient to ICU, giving a patient oxygen therapy, or putting a patient on a mechanical ventilator,’ he said.

‘The promising results in this study show that artificial intelligence has a strong potential to be an effective tool for supporting frontline healthcare workers in their decisions and improving clinical efficiency, which is especially important given how much stress the ongoing pandemic has placed on healthcare systems around the world.’

The research paper, ‘Towards computer-aided severity assessment via deep neural networks for geographic ad opacity extent scoring of SAR-CoV-2 chest X-rays’ is published in the journal Scientific Reports.

By Marvellous Iwendi.

Source: Waterloo News